Video Captioning Evaluation on WebVid 10M
61.377CLIP ScoreNoise
Evaluation results
| Method | Links | ||
|---|---|---|---|
| NoiseBase model=Video-ChatGPT2025.03 | 61.377 | 1.123 | |
| OriginalBase model=Video-ChatGPT2025.03 | 60.938 | 1.04 | |
| OriginalBase model=Video-LLaMA2025.03 | 60.889 | 0.316 | |
| NoiseBase model=Video-LLaMA2025.03 | 60.156 | 0.292 | |
| OriginalBase model=Video-Vicuna2025.03 | 60.107 | 1.332 | |
| NoiseBase model=Video-Vicuna2025.03 | 60.107 | 1.435 | |
| Rambling-FBase model=Video-ChatGPT2025.03 | 49.561 | 0.514 | |
| Rambling-LBase model=Video-ChatGPT2025.03 | 48.315 | 0.169 | |
| Rambling-LBase model=Video-Vicuna2025.03 | 44.189 | 0.449 | |
| Rambling-LBase model=Video-LLaMA2025.03 | 43.384 | 0.189 | |
| Rambling-FBase model=Video-LLaMA2025.03 | 42.896 | 0.205 | |
| Rambling-FBase model=Video-Vicuna2025.03 | 42.31 | 0.363 |